Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A new study from arXiv finds that test-time adaptation (TTA) can improve zero-shot 3D CT vision-language models only under specific conditions, and introduces CARVE (Cardinality-Aware Retained-View Entropy) as the first …
A pre-training Partial Information Decomposition framework that ranks multi-contrast 3D MRI input pairs by their redundant, unique, and synergistic information about regional tumor burden selected T1c+T2-FLAIR as the opt…
A new study from arXiv (2607.15439v1) finds that a verification-based coding agent using gpt-5.6-sol fully solves every public ARC-AGI-3 game at both high and max reasoning effort, achieving about 99% RHAE with fewer tha…
Researchers introduced MAR-12, a framework using Vision Language Models (VLMs) to detect and explain harmful humor in memes, achieving up to 80.3% accuracy for humor detection and 75.9% for hate detection on the PrideMM …
A new study from arXiv:2607.15449v1 applies renormalization group theory to Transformer attention, finding that attention's relevance depends on data correlation length. For long-correlation sequences, attention is a rel…
Researchers introduce ToolVerse, a framework that scales up agentic reinforcement learning environments using nearly 400 real-world Model Context Protocols containing about 4,500 tools, enabling LLM agents to perform com…
Researchers propose BIRD (Bootstrapped Iterative Self-Reasoning Distillation), a two-stage method that improves compressed reasoning by first generating concise, correct traces from a base model under a brevity instructi…
A new study from arXiv reveals that video pretrained backbones underperform on AI-generated video detection due to excessive spatiotemporal aggregation in their readout layers, which suppresses local temporal dynamics. T…
A new position paper on arXiv (2607.15313v1) argues that applying probabilistic scaling to quantum circuit synthesis is a directional error, because quantum circuits require strict mathematical constraints that create a …
Researchers propose MGDT, a novel framework for Multimodal Knowledge Graph Completion that uses a Relation-Adaptive Semantic Routing Mixture-of-Experts module to select relation-relevant multimodal features and a frozen …
A new method called Object-Part Hierarchical Reflective Grounding (OP-HRG) improves part-level visual grounding in multimodal large language models by introducing a coarse-to-fine reasoning pipeline that first localizes …
A new study comparing handcrafted feature descriptors and convolutional neural networks (CNNs) for facial expression recognition finds that CNNs achieve the best overall performance across three datasets (FER-2013, CK+, …
Researchers propose LLM4EHR, a clinical foundation model that aligns time series data with medical event sequences using large language models, achieving improved performance on downstream ICU prediction tasks. The model…
Researchers at an undisclosed institution found that masked diffusion language models (DLMs) learn a bidirectional induction circuit for in-context learning, where previous-token and next-token heads write local context …
A new closed-loop AutoML framework using GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers achieves mean test accuracies above 93% and a best accuracy of 98.1% for cross-lingual handwritten O…
A new study from arXiv (2607.15485v1) resolves the paradox of score-based generative models failing to learn correct mixture weights despite covering all modes, showing that generated samples can recover weights accurate…
A population-level machine learning analysis of Medical Expenditure Panel Survey data found that healthcare financial vulnerability after COVID-19 remained strongly associated with poverty status, insurance coverage, and…
Researchers present S1-Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation that consolidates fragmented AI4S capabilities into a single model. Trained on the S1-Omni-Corpus…
Researchers propose E3DGS, a unified geometric-photometric equivariant architecture for 3D Gaussian Splatting that treats color as a geometric entity via a matrix embedding, achieving SE(3) equivariance without Clebsch-G…
A new framework called Epipolar Distillation (EpiDistill) transfers scale-aware geometric priors from multi-view models into monocular depth foundation models, significantly improving zero-shot metric depth estimation on…